CN114625442A - Cold start recommendation method and device, electronic equipment and readable storage medium - Google Patents
Cold start recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN114625442A CN114625442A CN202210283460.4A CN202210283460A CN114625442A CN 114625442 A CN114625442 A CN 114625442A CN 202210283460 A CN202210283460 A CN 202210283460A CN 114625442 A CN114625442 A CN 114625442A
- Authority
- CN
- China
- Prior art keywords
- user
- registered
- registration
- behavior information
- cold start
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Abstract
The invention relates to an artificial intelligence technology, and discloses a cold start recommendation method, which comprises the following steps: the method comprises the steps of constructing a user registration behavior collection event set, collecting a registration behavior information set of a user to be registered based on the user registration behavior collection event set, judging malicious registration of the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result, classifying types of the user to be registered by utilizing the malicious registration result and the registration behavior information set to obtain a classification result, and recommending cold start of the user to be registered based on the classification result. Furthermore, the invention relates to blockchain techniques, the classification results may be stored in nodes of the blockchain. The invention also provides a cold start recommendation device, electronic equipment and a readable storage medium. The method and the device can solve the problem of low cold start recommendation accuracy.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a cold start recommendation method and device, electronic equipment and a readable storage medium.
Background
In the absence of valuable data of the user based on the application scenario correlation, how to make effective recommendations is called: "Cold Start problem". The cold start problem is one that the recommendation system must face. Currently, the general mainstream cold start strategies are classified into the following three categories: 1. a rule-based cold start process; 2. enriching the user and item features available during cold start; 3. active learning, migratory learning, and "exploration and utilization" mechanisms are utilized.
The problems in the prior art are that new user registration belongs to a standard process, new user registration information belongs to static characteristics and cannot be directly used for recommending cold start, user and article characteristics are difficult to obtain accurately, cold start recommendation based on mechanisms such as rules and active learning is difficult to adapt to new registered users, malicious registration is difficult to identify, and the accuracy rate of cold start recommendation is low.
Disclosure of Invention
The invention provides a cold start recommendation method and device, electronic equipment and a readable storage medium, and mainly aims to solve the problem of low cold start recommendation accuracy.
In order to achieve the above object, the present invention provides a cold start recommendation method, including:
constructing a user registration behavior collection event set;
collecting a registration behavior information set of a user to be registered based on the user registration behavior collection event set;
carrying out malicious registration judgment on the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result;
classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result;
and performing cold start recommendation on the user to be registered based on the classification result.
Optionally, the constructing a user registration behavior collection event set includes:
constructing a plurality of registered behavior event types;
and constructing a plurality of buried point events of the plurality of registration behavior event types by using a Key-Value form, summarizing and constructing all the buried point events, and obtaining the user registration behavior collection event set.
Optionally, the collecting a set of registration behavior information of a user to be registered based on the set of user registration behavior collection events includes:
collecting click behavior information of the user to be registered by using click events in the user registration behavior collection event set;
collecting browsing behavior information of the user to be registered by using browsing events in the user registration behavior collection event set;
utilizing the exposure events in the user registration behavior collection event set to collect the exposure behavior information of the user to be registered;
and summarizing the click behavior information, the browsing behavior information and the exposure behavior information to obtain the registration behavior information set.
Optionally, the judging malicious registration of the user to be registered by using the registration behavior information set includes:
judging whether the browsing behavior information meets a preset browsing duration threshold value or not;
if the browsing behavior information does not meet the browsing duration threshold, performing to determine that the user to be registered is maliciously registered;
if the browsing behavior information meets the browsing duration threshold, executing to judge whether the IP address of the user to be registered is a registered IP;
if the IP address of the user to be registered is the registered IP, executing to determine that the user to be registered is malicious registration;
and if the IP address of the user to be registered is not the registered IP, executing to determine that the user to be registered is non-malicious registration.
Optionally, the classifying the type of the user to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result includes:
acquiring a historical registration behavior information set of a registered user;
clustering the historical registration behavior information set by using a K-Means clustering algorithm to obtain a plurality of clustering clusters, and using the clustering clusters as classification types;
and performing type clustering on a registration behavior information set corresponding to a user to be registered which is not maliciously registered, and taking a classification type obtained by clustering as the classification result.
Optionally, the performing type clustering on the registration behavior information set corresponding to the non-maliciously registered user to be registered, and using a classification type obtained by clustering as the classification result includes:
performing vector normalization processing on the behavior information in the registration behavior information set to obtain a behavior vector;
calculating Euclidean distances between the behavior vectors and each clustering cluster in the classification type;
and determining the classification type corresponding to the clustering cluster with the minimum Euclidean distance as the classification result.
Optionally, the recommending, based on the classification result, the cold start of the user to be registered includes:
and pushing the information with the largest number of clicks of the historical users in the classification result to the user to be registered.
In order to solve the above problem, the present invention also provides a cold start recommendation device, including:
the behavior collection event construction module is used for constructing a user registration behavior collection event set;
the behavior information collection module is used for collecting a registration behavior information set of the user to be registered based on the user registration behavior collection event set;
the malicious registration judgment module is used for judging malicious registration of the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result;
and the cold start recommending module is used for classifying the types of the users to be registered by utilizing the malicious registration result and the registration behavior information set to obtain a classification result, and carrying out cold start recommendation on the users to be registered based on the classification result.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one computer program; and
and the processor executes the computer program stored in the memory to realize the cold start recommendation method.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the cold start recommendation method described above.
According to the invention, the user registration behavior collection event set is constructed, and the registration behavior information set of the user to be registered is collected based on the user registration behavior collection event set, so that the user behavior information can be collected to the maximum extent, and the malicious registration judgment is carried out by using the registration behavior information, thereby improving the accuracy of malicious registration identification. Meanwhile, the malicious registration result and the registration behavior information set are used for classifying the types of the users to be registered, the registration behavior information is classified, the behavior data of the users can be extracted from the standardized user registration process to the maximum extent, cold start recommendation is carried out on the users to be registered according to the classification result, and the accuracy of the cold start recommendation of the users is improved. Therefore, the cold start recommendation method, the cold start recommendation device, the electronic equipment and the computer readable storage medium provided by the invention can solve the problem of low cold start recommendation accuracy.
Drawings
Fig. 1 is a flowchart illustrating a cold start recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart showing a detailed implementation of one of the steps in FIG. 1;
FIG. 3 is a schematic flow chart showing another step of FIG. 1;
FIG. 4 is a schematic flow chart showing another step of FIG. 1;
FIG. 5 is a schematic flow chart showing another step in FIG. 1;
FIG. 6 is a flow chart illustrating a detailed implementation of one of the steps in FIG. 5;
FIG. 7 is a functional block diagram of a cold start recommendation device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device implementing the cold start recommendation method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a cold start recommendation method. The execution subject of the cold-start recommendation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the cold start recommendation method may be executed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Fig. 1 is a schematic flowchart of a cold start recommendation method according to an embodiment of the present invention. In the present embodiment, the cold start recommendation method includes the following steps S1-S5:
and S1, constructing a user registration behavior collection event set.
In the embodiment of the invention, the user registration behavior collection event refers to the behavior data of the user in the registration page, and the user registration behavior collection event can be constructed through a front-end buried point. For example, in the registration page, the set of user registration behavior collection events may include click-type events, browse-type events, exposure-type events, and the like.
In detail, referring to fig. 2, the building of the user registration behavior collection event set includes the following steps S10-S11:
s10, constructing a plurality of registration behavior event types;
s11, constructing a plurality of buried point events of the plurality of registered behavior event types by using a Key-Value form, summarizing and constructing all the buried point events, and obtaining the user registered behavior collection event set.
In the embodiment of the invention, a Key-Value-form buried point design rule means that a Key is an event and can correspond to the Value of one or more values corresponding to the event. For example, the event type is Click-type event (Click), the Key includes Page and Info bar, where Value when the Key is Page is Enter and Jump, which respectively indicates that entry to a login Page is recorded once, and jumping to other pages is recorded once; value when Key is Info bar is ActivityA and ActivityB, respectively indicating that information column A is selected to record once, and information column B is selected to record once.
In an optional embodiment of the present invention, the set of user registration behavior collection events includes click events, browse events, and exposure events.
In the embodiment of the invention, a plurality of buried point events are created by constructing the event type, so that the flexibility and the accuracy of the collection of the registration behavior events are improved.
And S2, collecting the registration behavior information set of the user to be registered based on the user registration behavior collection event set.
In the embodiment of the present invention, the registration behavior information set of the user to be registered refers to behavior information of the user on a registration page, and includes: 1. the order of filling in information when the user registers; 2. filling time information (pause time, filling time, etc.) of a certain information field; 3. whether the filling process has jump behavior.
Specifically, referring to fig. 3, the collecting the set of registration behavior information of the user to be registered based on the set of user registration behavior collection events includes the following steps S20-S23:
s20, collecting the click behavior information of the user to be registered by using the click events in the user registration behavior collection event set;
s21, collecting the browsing behavior information of the user to be registered by using the browsing event in the user registration behavior collection event set;
s22, collecting the exposure behavior information of the user to be registered by using the exposure events in the user registration behavior collection event set;
and S23, summarizing the click behavior information, the browsing behavior information and the exposure behavior information to obtain the registration behavior information set.
The click behavior information records a sequence triggered by a user clicking a certain object of a page, the browsing behavior information comprises browsing duration of the user, filling time for filling a certain information column and the like, and the exposure behavior information records the browsing times of the page by the user.
In an optional embodiment of the invention, as the user registration stage belongs to a standard process, the new user registration information belongs to a static characteristic and cannot be directly used for cold start recommendation, and the registration behavior information of the user is collected through a behavior event, so that the accuracy of analyzing the new user can be improved.
And S3, performing malicious registration judgment on the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result.
In the embodiment of the invention, the malicious registration judgment refers to judging whether the user to be registered is a real user or machine batch registration.
In detail, referring to fig. 4, the determining that the user to be registered is maliciously registered by using the registration behavior information set includes the following steps S30 to S34:
s30, judging whether the browsing behavior information meets a preset browsing duration threshold value;
if the browsing behavior information does not meet the browsing duration threshold, executing S31 and determining that the user to be registered is maliciously registered;
if the browsing behavior information meets the browsing duration threshold, executing S32, and judging whether the IP address of the user to be registered is a registered IP;
if the IP address of the user to be registered is the registered IP, executing S33 and determining that the user to be registered is malicious registration;
and if the IP address of the user to be registered is not the registered IP, executing S34 and determining that the user to be registered is non-malicious registration.
In the embodiment of the invention, as the time length of the malicious registration of the machine is shorter, the malicious registered user can be identified by setting the browsing time length threshold (for example, 30-60 seconds), whether the IP address of the user is the registered IP is judged, and the malicious registration is determined for the registered IP. The invention can improve the accuracy of identifying the malicious registered user by performing double verification on the behavior information and the IP of the user.
And S4, classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result.
In the embodiment of the invention, the type classification refers to classifying the new user to be registered by using the behavior data of the historical user.
Specifically, referring to fig. 5, the classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result includes the following steps S40-S42:
s40, acquiring a historical registration behavior information set of the registered user;
s41, clustering the historical registration behavior information set by using a K-Means clustering algorithm to obtain a plurality of clustering clusters, and taking the clustering clusters as classification types;
and S42, performing type clustering on the registration behavior information set corresponding to the user to be registered which is not maliciously registered, and taking the classified type obtained by clustering as the classification result.
In the embodiment of the invention, the K-Means clustering algorithm is an unsupervised clustering algorithm, and for a given sample set, the sample set is divided into K clustering clusters (namely K categories) according to the distance between samples, so that points in the clusters are connected together as closely as possible, and the distance between the clusters is as large as possible. For example, in the financial field, the classification type can be obtained by clustering: "high risk user", "medium risk user", "low risk user", etc.
In detail, referring to fig. 6, the performing type clustering on the registration behavior information set corresponding to the non-malicious registered user to be registered, and using the classified type obtained by clustering as the classification result includes the following steps S420 to S422:
s420, performing vector normalization processing on the behavior information in the registered behavior information set to obtain a behavior vector;
s421, calculating Euclidean distances between the behavior vectors and each cluster in the classification type;
s422, determining the classification type corresponding to the clustering cluster with the minimum Euclidean distance as the classification result.
In another optional embodiment of the present invention, the registration behavior information set is added into the historical registration behavior information set, and the new classification type is obtained by performing the above operation again.
In the embodiment of the invention, the historical users are classified through the clustering algorithm, the new user to be registered is matched with the historical users, and the new user to be registered can be effectively classified based on the historical users, so that the accuracy of cold start recommendation is improved.
And S5, performing cold start recommendation on the user to be registered based on the classification result.
In the embodiment of the invention, based on the classification result of the new user to be registered, the cold start recommendation of the new user can be performed according to the recommendation result of the similar historical user aiming at the recommendation scene. For example, in the financial field, if the classification result of the user to be registered is a "medium risk user", the recommendation result of the type of the medium risk user "is pushed to the user to be registered.
In detail, the recommending the cold start of the user to be registered based on the classification result includes:
and pushing the information with the largest number of clicks of the historical users in the classification result to the user to be registered.
In the embodiment of the invention, by taking the financial field as an example, the product information XXX fund No. 1 with the maximum number of clicks of the historical users of the type of middle risk users is pushed to the user to be registered.
According to the invention, the user registration behavior collection event set is constructed, and the registration behavior information set of the user to be registered is collected based on the user registration behavior collection event set, so that the user behavior information can be collected to the maximum extent, and the malicious registration judgment is carried out by using the registration behavior information, thereby improving the accuracy of malicious registration identification. Meanwhile, the malicious registration result and the registration behavior information set are used for classifying the types of the users to be registered, the registration behavior information is classified, the behavior data of the users can be extracted from the standardized user registration process to the maximum extent, cold start recommendation is carried out on the users to be registered according to the classification result, and the accuracy of the cold start recommendation of the users is improved. Therefore, the cold start recommendation method provided by the invention can solve the problem of low cold start recommendation accuracy.
Fig. 7 is a functional block diagram of a cold start recommendation device according to an embodiment of the present invention.
The cold start recommendation device 100 of the present invention can be installed in an electronic device. According to the implemented functions, the cold start recommendation device 100 may include a behavior collection event construction module 101, a behavior information collection module 102, a malicious registration judgment module 103, and a cold start recommendation module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the behavior collection event construction module 101 is configured to construct a user registration behavior collection event set;
the behavior information collection module 102 is configured to collect a registration behavior information set of a user to be registered based on the user registration behavior collection event set;
the malicious registration judgment module 103 is configured to perform malicious registration judgment on the user to be registered by using the registration behavior information set, so as to obtain a malicious registration result;
the cold start recommendation module 104 is configured to perform type classification on the user to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result, and perform cold start recommendation on the user to be registered based on the classification result.
In detail, the specific implementation of each module of the cold start recommendation device 100 is as follows:
step one, constructing a user registration behavior collection event set.
In the embodiment of the invention, the user registration behavior collection event is used for collecting behavior data of a user in a registration page, and can be constructed through a front-end buried point. For example, in the registration page, the set of user registration behavior collection events may include click-type events, browse-type events, exposure-type events, and the like.
In detail, the building a user registration behavior collection event set includes:
constructing a plurality of registered behavior event types;
and constructing a plurality of buried point events of the plurality of registration behavior event types by using a Key-Value form, summarizing and constructing all the buried point events, and obtaining the user registration behavior collection event set.
In the embodiment of the invention, a Key-Value-form buried point design rule means that a Key is an event and can correspond to the Value of one or more values corresponding to the event. For example, the event type is Click-type event (Click), the Key includes Page and Info bar, where Value when the Key is Page is Enter and Jump, which respectively indicates that entry to a login Page is recorded once, and jumping to other pages is recorded once; value when Key is Info bar is ActivityA and ActivityB, which respectively indicate that the selected information column A is recorded once and the selected information column B is recorded once.
In an optional embodiment of the present invention, the set of user registration behavior collection events includes a click event, a browse event, and an exposure event.
In the embodiment of the invention, a plurality of buried point events are created by constructing the event type, so that the flexibility and the accuracy of the collection of the registration behavior events are improved.
And secondly, collecting a registration behavior information set of the user to be registered based on the user registration behavior collection event set.
In the embodiment of the present invention, the registration behavior information set of the user to be registered refers to behavior information of the user on a registration page, and includes: 1. the order of filling in information when the user registers; 2. filling time information (pause time, filling time, etc.) of a certain information field; 3. whether the filling process has jump behavior.
Specifically, the collecting a set of registration behavior information of a user to be registered based on the set of user registration behavior collection events includes:
collecting click behavior information of the user to be registered by using click events in the user registration behavior collection event set;
collecting browsing behavior information of the user to be registered by using browsing events in the user registration behavior collection event set;
utilizing the exposure events in the user registration behavior collection event set to collect the exposure behavior information of the user to be registered;
and summarizing the click behavior information, the browsing behavior information and the exposure behavior information to obtain the registration behavior information set.
The method comprises the steps of obtaining click behavior information, obtaining browsing behavior information and exposure behavior information, wherein the click behavior information records the triggering sequence of a certain object of a clicked page of a user, the browsing behavior information comprises browsing duration of the user, filling time for filling in a certain information column and the like, and the exposure behavior information records the browsing times of the page by the user.
In an optional embodiment of the invention, as the user registration stage belongs to the standard process, the new user registration information belongs to the static characteristic and cannot be directly used for cold start recommendation, and the registration behavior information of the user is collected through the behavior event, so that the accuracy of analyzing the new user can be improved.
And thirdly, judging malicious registration of the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result.
In the embodiment of the invention, the malicious registration judgment refers to judging whether the user to be registered is a real user or machine batch registration.
In detail, the judging malicious registration of the user to be registered by using the registration behavior information set includes:
judging whether the browsing behavior information meets a preset browsing duration threshold value;
if the browsing behavior information does not meet the browsing duration threshold, performing to determine that the user to be registered is maliciously registered;
if the browsing behavior information meets the browsing duration threshold, executing to judge whether the IP address of the user to be registered is a registered IP;
if the IP address of the user to be registered is the registered IP, executing to determine that the user to be registered is malicious registration;
and if the IP address of the user to be registered is not the registered IP, executing to determine that the user to be registered is non-malicious registration.
In the embodiment of the invention, as the time length of the malicious registration of the machine is shorter, the malicious registered user can be identified by setting the browsing time length threshold (for example, 30-60 seconds), whether the IP address of the user is the registered IP is judged, and the malicious registration is determined for the registered IP. The invention can improve the accuracy of identifying the malicious registered user by performing double verification on the behavior information and the IP of the user.
And fourthly, classifying the types of the users to be registered by utilizing the malicious registration result and the registration behavior information set to obtain a classification result.
In the embodiment of the invention, the type classification refers to classifying the new user to be registered by using the behavior data of the historical user.
Specifically, the classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result includes:
acquiring a historical registration behavior information set of a registered user;
clustering the historical registration behavior information set by using a K-Means clustering algorithm to obtain a plurality of clustering clusters, and using the clustering clusters as classification types;
and performing type clustering on a registration behavior information set corresponding to a user to be registered which is not maliciously registered, and taking a classification type obtained by clustering as the classification result.
In the embodiment of the invention, the K-Means clustering algorithm is an unsupervised clustering algorithm, and for a given sample set, the sample set is divided into K clustering clusters (namely K categories) according to the distance between samples, so that points in the clusters are connected together as closely as possible, and the distance between the clusters is as large as possible. For example, in the financial field, the classification type can be obtained by clustering: "high risk user", "medium risk user", "low risk user", etc.
In detail, the performing type clustering on the registration behavior information set corresponding to the non-maliciously registered user to be registered, and using the classified type obtained by clustering as the classification result includes:
performing vector normalization processing on the behavior information in the registration behavior information set to obtain a behavior vector;
calculating Euclidean distances between the behavior vectors and each clustering cluster in the classification type;
and determining the classification type corresponding to the clustering cluster with the minimum Euclidean distance as the classification result.
In another optional embodiment of the present invention, the registration behavior information set is added into a history registration behavior information set, and the K-Means clustering algorithm is performed again to cluster the history registration behavior information set to obtain a new classification type.
In the embodiment of the invention, the historical users are classified through the clustering algorithm, the new user to be registered is matched with the historical users, and the new user to be registered can be effectively classified based on the historical users, so that the accuracy of cold start recommendation is improved.
And fifthly, performing cold start recommendation on the user to be registered based on the classification result.
In the embodiment of the invention, based on the classification result of the new user to be registered, the cold start recommendation of the new user can be performed according to the recommendation result of the similar historical user aiming at the recommendation scene. For example, in the financial field, if the classification result of the user to be registered is a "medium risk user", the recommendation result of the type of the medium risk user "is pushed to the user to be registered.
In detail, the recommending the cold start of the user to be registered based on the classification result includes:
and pushing the information with the largest number of clicks of the historical users in the classification result to the user to be registered.
In the embodiment of the invention, by taking the financial field as an example, the product information XXX fund No. 1 with the largest number of clicks of the historical users of the type of the 'middle risk users' is pushed to the user to be registered.
According to the invention, the user registration behavior collection event set is constructed, and the registration behavior information set of the user to be registered is collected based on the user registration behavior collection event set, so that the user behavior information can be collected to the maximum extent, and the malicious registration judgment is carried out by using the registration behavior information, thereby improving the accuracy of malicious registration identification. Meanwhile, the malicious registration result and the registration behavior information set are used for classifying the types of the users to be registered, the registration behavior information is classified, the behavior data of the users can be extracted from the standardized user registration process to the maximum extent, cold start recommendation is carried out on the users to be registered according to the classification result, and the accuracy of the cold start recommendation of the users is improved. Therefore, the cold start recommendation device provided by the invention can solve the problem of low cold start recommendation accuracy.
Fig. 8 is a schematic structural diagram of an electronic device implementing a cold start recommendation method according to an embodiment of the present invention.
The electronic device may comprise a processor 10, a memory 11, a communication interface 12 and a bus 13, and may further comprise a computer program, such as a cold start recommendation program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as a code of a cold start recommendation program, etc., but also to temporarily store data that has been output or is to be output.
The processor 10 may be formed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed of a plurality of integrated circuits packaged with the same function or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., a cold start recommendation program, etc.) stored in the memory 11 and calling data stored in the memory 11.
The communication interface 12 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
The bus 13 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus 13 may be divided into an address bus, a data bus, a control bus, etc. The bus 13 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 8 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 8 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the electronic device may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The cold start recommendation program stored in the memory 11 of the electronic device is a combination of a plurality of instructions, which when executed in the processor 10, can implement:
constructing a user registration behavior collection event set;
collecting a registration behavior information set of a user to be registered based on the user registration behavior collection event set;
carrying out malicious registration judgment on the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result;
classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result;
and performing cold start recommendation on the user to be registered based on the classification result.
Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.
Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
constructing a user registration behavior collection event set;
collecting a registration behavior information set of a user to be registered based on the user registration behavior collection event set;
carrying out malicious registration judgment on the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result;
classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result;
and performing cold start recommendation on the user to be registered based on the classification result.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A cold start recommendation method, the method comprising:
constructing a user registration behavior collection event set;
collecting a registration behavior information set of a user to be registered based on the user registration behavior collection event set;
carrying out malicious registration judgment on the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result;
classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result;
and performing cold start recommendation on the user to be registered based on the classification result.
2. The cold start recommendation method of claim 1, wherein said constructing a set of user registration behavior collection events comprises:
constructing a plurality of registered behavior event types;
and constructing a plurality of buried point events of the plurality of registration behavior event types by using a Key-Value form, summarizing and constructing all the buried point events, and obtaining the user registration behavior collection event set.
3. The cold-start recommendation method of claim 2, wherein said collecting a set of registration behavior information of a user to be registered based on said set of user registration behavior collection events comprises:
collecting click behavior information of the user to be registered by using click events in the user registration behavior collection event set;
collecting browsing behavior information of the user to be registered by using browsing events in the user registration behavior collection event set;
utilizing the exposure events in the user registration behavior collection event set to collect the exposure behavior information of the user to be registered;
and summarizing the click behavior information, the browsing behavior information and the exposure behavior information to obtain the registration behavior information set.
4. The cold-start recommendation method according to claim 3, wherein the determining malicious registration of the user to be registered by using the registration behavior information set includes:
judging whether the browsing behavior information meets a preset browsing duration threshold value;
if the browsing behavior information does not meet the browsing duration threshold, performing to determine that the user to be registered is maliciously registered;
if the browsing behavior information meets the browsing duration threshold, executing to judge whether the IP address of the user to be registered is a registered IP;
if the IP address of the user to be registered is the registered IP, executing to determine that the user to be registered is malicious registration;
and if the IP address of the user to be registered is not the registered IP, executing to determine that the user to be registered is non-malicious registration.
5. The method according to claim 1, wherein the classifying the types of the users to be registered by using the malicious registration result and the registration behavior information set to obtain a classification result includes:
acquiring a historical registration behavior information set of a registered user;
clustering the historical registration behavior information set by using a K-Means clustering algorithm to obtain a plurality of clustering clusters, and taking the clustering clusters as classification types;
and performing type clustering on a registration behavior information set corresponding to a user to be registered which is not maliciously registered, and taking a classification type obtained by clustering as the classification result.
6. The cold-start recommendation method according to claim 5, wherein the performing type clustering on the registration behavior information sets corresponding to the non-maliciously registered users to be registered, and using the classified types obtained by the clustering as the classification results includes:
performing vector normalization processing on the behavior information in the registration behavior information set to obtain a behavior vector;
calculating Euclidean distances between the behavior vectors and each cluster in the classification type;
and determining the classification type corresponding to the clustering cluster with the minimum Euclidean distance as the classification result.
7. The cold start recommendation method according to any one of claims 1 to 6, wherein the performing cold start recommendation on the user to be registered based on the classification result comprises:
and pushing the information with the largest number of clicks of the historical users in the classification result to the user to be registered.
8. A cold start recommendation device, the device comprising:
the behavior collection event construction module is used for constructing a user registration behavior collection event set;
the behavior information collection module is used for collecting a registration behavior information set of the user to be registered based on the user registration behavior collection event set;
the malicious registration judgment module is used for judging malicious registration of the user to be registered by utilizing the registration behavior information set to obtain a malicious registration result;
and the cold start recommending module is used for classifying the types of the users to be registered by utilizing the malicious registration result and the registration behavior information set to obtain a classification result, and carrying out cold start recommendation on the users to be registered based on the classification result.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of cold start recommendation of any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a cold start recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210283460.4A CN114625442A (en) | 2022-03-22 | 2022-03-22 | Cold start recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210283460.4A CN114625442A (en) | 2022-03-22 | 2022-03-22 | Cold start recommendation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114625442A true CN114625442A (en) | 2022-06-14 |
Family
ID=81904098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210283460.4A Pending CN114625442A (en) | 2022-03-22 | 2022-03-22 | Cold start recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114625442A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110043842A (en) * | 2009-10-22 | 2011-04-28 | 성균관대학교산학협력단 | User adaptive recommendation system |
| CN102946319A (en) * | 2012-09-29 | 2013-02-27 | 焦点科技股份有限公司 | System and method for analyzing network user behavior information |
| CN111105263A (en) * | 2018-10-29 | 2020-05-05 | 北京奇虎科技有限公司 | User identification method and device, electronic equipment and storage medium |
| CN111523035A (en) * | 2020-04-24 | 2020-08-11 | 上海异势信息科技有限公司 | Recommendation method, device, server and medium for APP browsing content |
| CN111556059A (en) * | 2020-04-29 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Abnormity detection method, abnormity detection device and terminal equipment |
-
2022
- 2022-03-22 CN CN202210283460.4A patent/CN114625442A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110043842A (en) * | 2009-10-22 | 2011-04-28 | 성균관대학교산학협력단 | User adaptive recommendation system |
| CN102946319A (en) * | 2012-09-29 | 2013-02-27 | 焦点科技股份有限公司 | System and method for analyzing network user behavior information |
| CN111105263A (en) * | 2018-10-29 | 2020-05-05 | 北京奇虎科技有限公司 | User identification method and device, electronic equipment and storage medium |
| CN111523035A (en) * | 2020-04-24 | 2020-08-11 | 上海异势信息科技有限公司 | Recommendation method, device, server and medium for APP browsing content |
| CN111556059A (en) * | 2020-04-29 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Abnormity detection method, abnormity detection device and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112231586A (en) | Course recommendation method, device, equipment and medium based on transfer learning | |
| CN111949708B (en) | Multi-task prediction method, device, equipment and medium based on time sequence feature extraction | |
| CN111860377A (en) | Live broadcast method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN111950621A (en) | Target data detection method, device, equipment and medium based on artificial intelligence | |
| CN113592605A (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN113806434A (en) | Big data processing method, device, equipment and medium | |
| CN114756669A (en) | Intelligent analysis method and device for problem intention, electronic equipment and storage medium | |
| CN114862140A (en) | Behavior analysis-based potential evaluation method, device, equipment and storage medium | |
| CN113434542B (en) | Data relationship identification method and device, electronic equipment and storage medium | |
| CN114185776A (en) | Big data point burying method, device, equipment and medium for application program | |
| CN113886204A (en) | User behavior data collection method and device, electronic equipment and readable storage medium | |
| WO2023272862A1 (en) | Risk control recognition method and apparatus based on network behavior data, and electronic device and medium | |
| CN113282854A (en) | Data request response method and device, electronic equipment and storage medium | |
| CN111950707A (en) | Behavior prediction method, apparatus, device and medium based on behavior co-occurrence network | |
| CN114841165B (en) | User data analysis and display method and device, electronic equipment and storage medium | |
| CN114662005A (en) | Message pushing method, device, equipment and storage medium for user behavior track | |
| CN115203364A (en) | Software fault feedback processing method, device, equipment and readable storage medium | |
| CN111859985B (en) | AI customer service model test method and device, electronic equipment and storage medium | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN114518993A (en) | System performance monitoring method, device, equipment and medium based on business characteristics | |
| CN114722280A (en) | User portrait based course recommendation method, device, equipment and storage medium | |
| CN114219367A (en) | User scoring method, device, equipment and storage medium | |
| CN114625442A (en) | Cold start recommendation method and device, electronic equipment and readable storage medium | |
| CN114723488B (en) | Course recommendation method and device, electronic equipment and storage medium | |
| CN113312564A (en) | Comment data sorting method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |